In recent years, unsupervised and self-supervised graph representation learning has gained popularity in the research community. However, most proposed methods are focused on homogeneous networks, whereas real-world graphs often contain multiple node and edge types. Multiplex graphs, a special type of heterogeneous graphs, possess richer information, provide better modeling capabilities and integrate more detailed data from potentially different sources. The diverse edge types in multiplex graphs provide more context and insights into the underlying processes of representation learning. In this paper, we tackle the problem of learning representations for nodes in multiplex networks in an unsupervised or self-supervised manner. To that end, we explore diverse information fusion schemes performed at different levels of the graph processing pipeline. The detailed analysis and experimental evaluation of various scenarios inspired us to propose improvements in how to construct GNN architectures that deal with multiplex graphs.
In recent years, self-supervised learning has played a pivotal role in advancing machine learning by allowing models to acquire meaningful representations from unlabeled data. An intriguing research avenue involves developing self-supervised models within an information-theoretic framework, but many studies often deviate from the stochasticity assumptions made when deriving their objectives. To gain deeper insights into this issue, we propose to explicitly model the representation with stochastic embeddings and assess their effects on performance, information compression and potential for out-of-distribution detection. From an information-theoretic perspective, we seek to investigate the impact of probabilistic modeling on the information bottleneck, shedding light on a trade-off between compression and preservation of information in both representation and loss space. Emphasizing the importance of distinguishing between these two spaces, we demonstrate how constraining one can affect the other, potentially leading to performance degradation. Moreover, our findings suggest that introducing an additional bottleneck in the loss space can significantly enhance the ability to detect out-of-distribution examples, only leveraging either representation features or the variance of their underlying distribution.
Document-level joint entity and relation extraction is a challenging information extraction problem that requires a unified approach where a single neural network performs four sub-tasks: mention detection, coreference resolution, entity classification, and relation extraction. Existing methods often utilize a sequential multi-task learning approach, in which the arbitral decomposition causes the current task to depend only on the previous one, missing the possible existence of the more complex relationships between them. In this paper, we present a multi-task learning framework with bidirectional memory-like dependency between tasks to address those drawbacks and perform the joint problem more accurately. Our empirical studies show that the proposed approach outperforms the existing methods and achieves state-of-the-art results on the BioCreative V CDR corpus.
The popularity of social media makes politicians use it for political advertisement. Therefore, social media is full of electoral agitation (electioneering), especially during the election campaigns. The election administration cannot track the spread and quantity of messages that count as agitation under the election code. It addresses a crucial problem, while also uncovering a niche that has not been effectively targeted so far. Hence, we present the first publicly open data set for detecting electoral agitation in the Polish language. It contains 6,112 human-annotated tweets tagged with four legally conditioned categories. We achieved a 0.66 inter-annotator agreement (Cohen's kappa score). An additional annotator resolved the mismatches between the first two improving the consistency and complexity of the annotation process. The newly created data set was used to fine-tune a Polish Language Model called HerBERT (achieving a 68% F1 score). We also present a number of potential use cases for such data sets and models, enriching the paper with an analysis of the Polish 2020 Presidential Election on Twitter.
Production deployments in complex systems require ML architectures to be highly efficient and usable against multiple tasks. Particularly demanding are classification problems in which data arrives in a streaming fashion and each class is presented separately. Recent methods with stochastic gradient learning have been shown to struggle in such setups or have limitations like memory buffers, and being restricted to specific domains that disable its usage in real-world scenarios. For this reason, we present a fully differentiable architecture based on the Mixture of Experts model, that enables the training of high-performance classifiers when examples from each class are presented separately. We conducted exhaustive experiments that proved its applicability in various domains and ability to learn online in production environments. The proposed technique achieves SOTA results without a memory buffer and clearly outperforms the reference methods.
Despite impressive advancements in multilingual corpora collection and model training, developing large-scale deployments of multilingual models still presents a significant challenge. This is particularly true for language tasks that are culture-dependent. One such example is the area of multilingual sentiment analysis, where affective markers can be subtle and deeply ensconced in culture. This work presents the most extensive open massively multilingual corpus of datasets for training sentiment models. The corpus consists of 79 manually selected datasets from over 350 datasets reported in the scientific literature based on strict quality criteria. The corpus covers 27 languages representing 6 language families. Datasets can be queried using several linguistic and functional features. In addition, we present a multi-faceted sentiment classification benchmark summarizing hundreds of experiments conducted on different base models, training objectives, dataset collections, and fine-tuning strategies.
Graph machine learning models have been successfully deployed in a variety of application areas. One of the most prominent types of models - Graph Neural Networks (GNNs) - provides an elegant way of extracting expressive node-level representation vectors, which can be used to solve node-related problems, such as classifying users in a social network. However, many tasks require representations at the level of the whole graph, e.g., molecular applications. In order to convert node-level representations into a graph-level vector, a so-called readout function must be applied. In this work, we study existing readout methods, including simple non-trainable ones, as well as complex, parametrized models. We introduce a concept of ensemble-based readout functions that combine either representations or predictions. Our experiments show that such ensembles allow for better performance than simple single readouts or similar performance as the complex, parametrized ones, but at a fraction of the model complexity.
Learning representations of nodes has been a crucial area of the graph machine learning research area. A well-defined node embedding model should reflect both node features and the graph structure in the final embedding. In the case of dynamic graphs, this problem becomes even more complex as both features and structure may change over time. The embeddings of particular nodes should remain comparable during the evolution of the graph, what can be achieved by applying an alignment procedure. This step was often applied in existing works after the node embedding was already computed. In this paper, we introduce a framework -- RAFEN -- that allows to enrich any existing node embedding method using the aforementioned alignment term and learning aligned node embedding during training time. We propose several variants of our framework and demonstrate its performance on six real-world datasets. RAFEN achieves on-par or better performance than existing approaches without requiring additional processing steps.
Continual learning with an increasing number of classes is a challenging task. The difficulty rises when each example is presented exactly once, which requires the model to learn online. Recent methods with classic parameter optimization procedures have been shown to struggle in such setups or have limitations like non-differentiable components or memory buffers. For this reason, we present the fully differentiable ensemble method that allows us to efficiently train an ensemble of neural networks in the end-to-end regime. The proposed technique achieves SOTA results without a memory buffer and clearly outperforms the reference methods. The conducted experiments have also shown a significant increase in the performance for small ensembles, which demonstrates the capability of obtaining relatively high classification accuracy with a reduced number of classifiers.
The availability of compute and data to train larger and larger language models increases the demand for robust methods of benchmarking the true progress of LM training. Recent years witnessed significant progress in standardized benchmarking for English. Benchmarks such as GLUE, SuperGLUE, or KILT have become de facto standard tools to compare large language models. Following the trend to replicate GLUE for other languages, the KLEJ benchmark has been released for Polish. In this paper, we evaluate the progress in benchmarking for low-resourced languages. We note that only a handful of languages have such comprehensive benchmarks. We also note the gap in the number of tasks being evaluated by benchmarks for resource-rich English/Chinese and the rest of the world. In this paper, we introduce LEPISZCZE (the Polish word for glew, the Middle English predecessor of glue), a new, comprehensive benchmark for Polish NLP with a large variety of tasks and high-quality operationalization of the benchmark. We design LEPISZCZE with flexibility in mind. Including new models, datasets, and tasks is as simple as possible while still offering data versioning and model tracking. In the first run of the benchmark, we test 13 experiments (task and dataset pairs) based on the five most recent LMs for Polish. We use five datasets from the Polish benchmark and add eight novel datasets. As the paper's main contribution, apart from LEPISZCZE, we provide insights and experiences learned while creating the benchmark for Polish as the blueprint to design similar benchmarks for other low-resourced languages.